SOTAVerified

Instruction Following

Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 951–975 of 1135 papers

TitleStatusHype
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models—0
SAIL: Search-Augmented Instruction Learning—0
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation—0
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain—0
Scalable Ensembling For Mitigating Reward Overoptimisation—0
Scalable Vision Language Model Training via High Quality Data Curation—0
ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting—0
Video Instruction Tuning With Synthetic Data—0
Video Unlearning via Low-Rank Refusal Vector—0
Argument Quality Assessment in the Age of Instruction-Following Large Language Models—0
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding—0
HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages—0
"Are you telling me to put glasses on the dog?'' Content-Grounded Annotation of Instruction Clarification Requests in the CoDraw Dataset—0
X-VILA: Cross-Modality Alignment for Large Language Model—0
SeedEdit 3.0: Fast and High-Quality Generative Image Editing—0
Are You Human? An Adversarial Benchmark to Expose LLMs—0
Vision-Language Models Provide Promptable Representations for Reinforcement Learning—0
Are We There Yet? Learning to Localize in Embodied Instruction Following—0
VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation—0
Self-Boosting Large Language Models with Synthetic Preference Data—0
Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation—0
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning—0
Self-Educated Language Agent with Hindsight Experience Replay for Instruction Following—0
HIGhER : Improving instruction following with Hindsight Generation for Experience Replay—0
Identifying Reliable Evaluation Metrics for Scientific Text RevisionCode0
Show:102550
← PrevPage 39 of 46Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AutoIF (Llama3 70B)Inst-level loose-accuracy90.4—Unverified
2AutoIF (Qwen2 72B)Inst-level loose-accuracy88—Unverified
3GPT-4Inst-level loose-accuracy85.37—Unverified
4PaLM 2 SInst-level loose-accuracy59.11—Unverified